SPIP to improve online serving of Spark MLLib Models

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

SPIP to improve online serving of Spark MLLib Models

aholler
Hi, Folks,

I have filed a JIRA ticket
(https://issues.apache.org/jira/browse/SPARK-26247) for
an SPIP on improving the model load latency and serving interfaces for MLLib
model
online serving, as discussed with Joseph Bradley and with Felix Cheung as
the SPIP Shepherd.
The associated SPIP doc is linked from the ticket.

We have been using the proposed code improvements to do online serving of
Spark MLLib models
in production at Uber, and have found the combination of Spark standard
on-disk model
representation with efficient loading and online serving to work well for
us.

Thanks in advance for any thoughts on this.

-Best regards, Anne Holler



--
Sent from: http://apache-spark-developers-list.1001551.n3.nabble.com/

---------------------------------------------------------------------
To unsubscribe e-mail: [hidden email]